Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 157 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.1196. Min Act: -0.0002

Data Index: 1002449 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.1148. Min Act: -0.0002

Data Index: 124223 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.0953. Min Act: -0.0002

Data Index: 183930 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.0823. Min Act: -0.0002

Data Index: 144259 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.0626. Min Act: -0.0002

Data Index: 45679 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.0801. Min Act: -0.0002

Data Index: 1168356 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.0217. Min Act: -0.0002

Data Index: 739943 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.0048. Min Act: -0.0002

Data Index: 350138 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 1.1196. Min Range: -1.1196

Max Act: 1.0083. Min Act: -0.0002

Data Index: 248688 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9800. Min Act: -0.0002

Data Index: 1351421 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9726. Min Act: -0.0002

Data Index: 390542 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9647. Min Act: -0.0002

Data Index: 1006337 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9766. Min Act: -0.0002

Data Index: 25850 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9348. Min Act: -0.0002

Data Index: 638096 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9391. Min Act: -0.0002

Data Index: 1256783 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9247. Min Act: -0.0002

Data Index: 1277703 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9449. Min Act: -0.0002

Data Index: 700098 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9366. Min Act: -0.0002

Data Index: 1034309 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9217. Min Act: -0.0002

Data Index: 548110 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 1.1196. Min Range: -1.1196

Max Act: 0.9256. Min Act: -0.0002

Data Index: 1042008 (C4 (Web Text))

Max Activating Token Index: 816